Related papers: Brain-like associative learning using a nanoscale …

Rapidly learning from ongoing experiences and remembering past events with a flexible memory system are two core capacities of biological intelligence. While the underlying neural mechanisms are not fully understood, various evidence…

Memory is a key component of biological neural systems that enables the retention of information over a huge range of temporal scales, ranging from hundreds of milliseconds up to years. While Hebbian plasticity is believed to play a pivotal…

A hallmark of biological intelligence is neural reuse,the ability to preserve past learning and repurpose it for new tasks and changing environments. Photonic neural hardware offers high-bandwidth, low-latency computation, but current…

Phase change memory (PCM) devices are known to reduce in power consumption as the bit volume and contact area of their electrodes are scaled down. Here, we demonstrate two types of low-power PCM devices with lateral graphene ribbon…

Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks. Neural networks, in particular, suffer plenty…

Neural networks are commonly trained to make predictions through learning algorithms. Contrastive Hebbian learning, which is a powerful rule inspired by gradient backpropagation, is based on Hebb's rule and the contrastive divergence…

Spiking neural networks (SNNs) are biologically inspired energy-efficient models that use sparse binary spike-based communication between neurons, making them attractive for resource-constrained edge devices. Federated learning enables such…

Thermodynamic-driven filament formation in redox-based resistive memory and the impact of thermal fluctuations on switching probability of emerging magnetic switches are probabilistic phenomena in nature, and thus, processes of binary…

On-chip learning in a crossbar array based analog hardware Neural Network (NN) has been shown to have major advantages in terms of speed and energy compared to training NN on a traditional computer. However analog hardware NN proposals and…

This paper presents an extension of the BrainScaleS accelerated analog neuromorphic hardware model. The scalable neuromorphic architecture is extended by the support for multi-compartment models and non-linear dendrites. These features are…

Nanoscale resistive switching devices (memristive devices or memristors) have been studied for a number of applications ranging from non-volatile memory, logic to neuromorphic systems. However a major challenge is to address the potentially…

Modern-day computers use electrical signaling for processing and storing data which is bandwidth limited and power-hungry. These limitations are bypassed in the field of communications, where optical signaling is the norm. To exploit…

For decades, conventional computers based on the von Neumann architecture have performed computation by repeatedly transferring data between their processing and their memory units, which are physically separated. As computation becomes…

Silicon-based analog neural networks physically embody the ideal neural network model in an approximate way. We show that by retraining the neural network using a physics-informed hardware-aware model one can fully recover the inference…

A fundamental feature of learning in animals is the "ability to forget" that allows an organism to perceive, model and make decisions from disparate streams of information and adapt to changing environments. Against this backdrop, we…

Despite the promise of superior efficiency and scalability, real-world deployment of emerging nanoelectronic platforms for brain-inspired computing have been limited thus far, primarily because of inter-device variations and intrinsic…

The standard Hopfield model for associative neural networks accounts for biological Hebbian learning and acts as the harmonic oscillator for pattern recognition, however its maximal storage capacity is $\alpha \sim 0.14$, far from the…

Resistive Random Access Memory (RRAM) and Phase Change Memory (PCM) devices have been popularly used as synapses in crossbar array based analog Neural Network (NN) circuit to achieve more energy and time efficient data classification…

We propose a design principle for the learning circuits of the biological brain. The principle states that almost any dendritic weights updated via heterosynaptic plasticity can implement a generalized and efficient class of gradient-based…

Associative memories in the brain receive and store patterns of activity registered by the sensory neurons, and are able to retrieve them when necessary. Due to their importance in human intelligence, computational models of associative…